Automated travel lane recommendation

Abstract

Various embodiments include an automated travel lane recommendation implemented for a vehicle in response to traffic conditions in the vehicle's vicinity, including characteristics of traffic flow of nearby lanes of travel. In some examples, sensors implemented as part of a vehicle collect data about available lanes and other vehicles and obstructions in the vicinity of the vehicle or along the vehicle's route of travel. According to some examples, sensor fusion logic processes sensor data to calculate metrics associated with traffic conditions relevant to the vehicle. In some embodiments, a preferred travel lane for the vehicle is calculated using a combination of a cost function of traffic metrics with other available information. The preferred travel lane is presented to an operator or control system of the vehicle in some examples. Information, such as preferred lane information, cost function information, and traffic condition metrics is shared with other vehicles and devices, or stored to a database in some examples.

What is claimed is: 
     
       1. A system, comprising:
 a plurality of sensors coupled to a vehicle, the plurality of sensors comprising:
 a first sensor coupled to the vehicle for detecting a plurality of travel lanes in the vicinity of the vehicle; and 
 a second sensor coupled to the vehicle for detecting a plurality of obstacles in the vicinity of the vehicle; and 
 
 a lane recommendation module configured to:
 receive data from the plurality of sensors; 
 analyze traffic conditions, wherein to analyze traffic conditions, the lane recommendation module is configured to:
 calculate, for each of multiple lanes of the plurality of travel lanes, a respective cost according to a cost function that takes into account weighted traffic metrics, wherein a respective value for at least one traffic metric of the weighted traffic metrics is determined using at least a portion of the data received from the plurality of sensors, and wherein a first traffic metric of the weighted traffic metrics has a different weight than a second traffic metric of the weighted traffic metrics; 
 
 identify a preferred travel lane of the plurality of travel lanes, the identification based, at least in part, on the analysis of traffic conditions; and 
 recommend the preferred travel lane. 
 
 
     
     
       2. The system of  claim 1 , wherein, to identify the preferred travel lane, the lane recommendation module is configured to consider information provided by a navigation system. 
     
     
       3. The system of  claim 1 , wherein identifying to identify the preferred travel lane, the lane recommendation module is configured to consider a destination of the vehicle. 
     
     
       4. The system of  claim 1 , wherein the traffic metrics comprise a flow rate. 
     
     
       5. The system of  claim 1 , wherein the weighted traffic metrics comprise:
 an average speed; 
 a standard deviation of speed; 
 an average traffic density; and 
 a bunching characteristic. 
 
     
     
       6. The system of  claim 1 , wherein, to recommend the preferred lane, the lane recommendation module is configured to cause a notification to be provided to an operator of the vehicle. 
     
     
       7. The system of  claim 1 , wherein the first sensor comprises a camera. 
     
     
       8. The system of  claim 7 , wherein the second sensor comprises a lidar detection sensor. 
     
     
       9. The system of  claim 8 , wherein the plurality of sensors further comprises a third sensor for detecting a velocity of at least one of the plurality of obstacles in the vicinity of the vehicle. 
     
     
       10. A method, comprising:
 receiving data from a plurality of sensors coupled to a vehicle, the plurality of sensors comprising:
 a first sensor coupled to the vehicle for detecting a plurality of travel lanes in the vicinity of the vehicle; and 
 a second sensor coupled to the vehicle for detecting a plurality of obstacles in the vicinity of the vehicle; 
 
 calculating, for each of multiple lanes of the plurality of travel lanes, a respective cost according to a cost function that takes into account weighted traffic metrics, wherein a respective value for at least one traffic metric of the weighted traffic metrics is determined using at least a portion of the data received from the plurality of sensors, and wherein a first traffic metric of the weighted traffic metrics has a different weight than a second traffic metric of the weighted traffic metrics; 
 identifying a preferred travel lane of the plurality of travel lanes, the identifying based, at least in part, on the respective cost; and 
 recommending the preferred travel lane. 
 
     
     
       11. The method of  claim 10 , wherein the weighted traffic metrics are weighted based at least in part on one or more of:
 user preferences; or 
 data associated with at least one driving habit of an operator of the vehicle. 
 
     
     
       12. The method of  claim 10 , further comprising receiving preferences of a user, wherein the identifying the preferred travel lane is based, at least in part, on the preferences of the user. 
     
     
       13. The method of  claim 10 , further comprising receiving data associated with at least one driving habit of an operator of the vehicle, wherein the identifying the preferred travel lane is based, at least in part, on at least a portion of the data associated with the at least one driving habit of the operator of the vehicle. 
     
     
       14. The method of  claim 10 , wherein recommending the preferred travel lane comprises presenting an indication of the preferred travel lane within a head-up display of the vehicle. 
     
     
       15. The method of  claim 10 , wherein recommending the preferred travel lane comprises identifying the preferred travel lane to an autonomous control system of the vehicle. 
     
     
       16. The method of  claim 10 , wherein the weighted traffic metrics comprise:
 an average speed; 
 a standard deviation of speed; 
 an average traffic density; and 
 a bunching characteristic. 
 
     
     
       17. The method of  claim 16 , wherein identifying a preferred travel lane comprises identifying the preferred travel lane as having a lowest cost among the multiple lanes according to the cost function. 
     
     
       18. A non-transitory, computer-readable storage medium storing program instructions that when executed by one or more computing devices cause the one or more computing devices to implement:
 receiving data from a plurality of sensors coupled to a vehicle, the plurality of sensors comprising:
 a first sensor coupled to the vehicle for detecting a plurality of travel lanes in the vicinity of the vehicle, the first sensor comprising a visible light camera; 
 a second sensor coupled to the vehicle for detecting a plurality of obstacles in the vicinity of the vehicle, the second sensor comprising a lidar detection sensor; and 
 a third sensor coupled to the vehicle for detecting a velocity of at least one of the plurality of obstacles in the vicinity of the vehicle, the third sensor comprising a radar sensor component; 
 
 calculating, for each of multiple lanes of the plurality of travel lanes, a respective cost according to a cost function that takes into account weighted traffic metrics, wherein a respective value for at least one traffic metric of the weighted traffic metrics is determined using at least a portion of the data received from the plurality of sensors, and wherein a first traffic metric of the weighted traffic metrics has a different weight than a second traffic metric of the weighted traffic metrics; 
 identifying a preferred travel lane of the plurality of travel lanes, the identifying based, at least in part, on the respective cost; and 
 recommending the preferred travel lane. 
 
     
     
       19. The non-transitory, computer-readable storage medium of  claim 18 , wherein the weighted traffic metrics comprise:
 an average speed; 
 a standard deviation of speed; 
 an average traffic density; and 
 a bunching characteristic. 
 
     
     
       20. The non-transitory, computer-readable storage medium of  claim 19 , wherein the weighted traffic metrics are weighted based, in part, on at least one of:
 preferences received from a user; or 
 data associated with at least one driving habit of an operator of the vehicle.